Tubask
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| youtube_queryA | Query YouTube: search videos/channels/playlists, channel profiles, latest uploads, playlist items, video comments, topic research with stats, or multi-video creator advice. Returns JSON including intent, result items, optional advice{} for goal=advice, next_steps[], and quota_cost. Single-video summaries and verbatim caption lookup use summarize_video and get_transcript. |
| summarize_videoA | Summarize one YouTube video from captions and metadata. Returns JSON with summary, key_points[], chapters[], quotes[] (timestamped), coverage{} (transcript sampling), and next_steps[]. Requires captions (auto-generated counts). Multi-video creator synthesis uses youtube_query with goal=advice. |
| get_transcriptA | Fetch YouTube captions for one video: full text, keyword search, time range, or paginated segments. Returns JSON with segments[] (display_timestamp, end_seconds), match_count when searching, language metadata, and next_steps[]. Structured overview of a video uses summarize_video. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool serves a clearly distinct purpose: youtube_query handles searching and channel/playlist/comment queries, summarize_video produces summaries from captions, and get_transcript returns raw caption text. There is no overlap in core functionality, and the descriptions explicitly cross-reference each other to clarify boundaries.
The tools all use lowercase snake_case but do not follow a uniform verb_noun pattern. 'summarize_video' and 'get_transcript' start with verbs, while 'youtube_query' starts with a noun, creating a slight inconsistency. However, the naming style is still predictable and readable.
With exactly three tools, the server is well-scoped and each tool is substantial. The count is within the ideal 3-15 range and covers the primary YouTube interaction modes without unnecessary bloat.
The server covers a broad range of YouTube data: searching, channel profiles, playlist items, comments, summaries, and transcripts. Minor gaps exist, such as no direct video metadata endpoint without a summary, but the existing tools work together to cover most reasonable use cases.